Keyframe Extraction and Process Recognition Method for Assembly Operation Based on Density Clustering

A keyframe extraction and process recognition method for assembly operations is proposed based on density clustering to solve the problems of data redundancy and difficulty in obtaining valid data frames from the process of continuous assembly operations. A standard operation gesture set, including dynamic and static actions, was constructed by decomposing the assembly operation. The finger feature variables and comprehensive gesture feature quantized function were defined according to the finger joint structure. Based on searching for local extreme points in the function, the density clustering method was used to extract the keyframes of the assembly operation sequence to eliminate redundant data. Finally, the support vector machine algorithm model and Levinstein distance were determined to complete the keyframe recognition and assembly operation matching. A case study demonstrated that the proposed method could effectively discretize the assembly operation sequence, remove approximately 84% of redundant data frames, and achieve a comprehensive recognition rate of 92%.